linear_getDocuments

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (readOnlyHint: true, idempotentHint: true, destructiveHint: false) fully cover the safety profile, so the description only needs to add context beyond that. The description's 'Get' is consistent with readOnly behavior, and it adds no contradictory information. However, it adds no additional behavioral context (e.g., pagination, return format, that it returns a list) beyond what the schema already indicates. With annotations present, the bar is lower, so a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, short sentence with no redundancy. It's concise and front-loaded, stating the action and resource immediately. However, it's almost too brief—given the tool's complexity (10 parameters, many filters), a slightly more detailed description would be more useful without becoming verbose. It earns a 4 for efficiency, losing a point for under-specification.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the presence of an output schema (which documents return values), the description is incomplete for a tool with this many optional filters and numerous sibling getters. It doesn't explain that this is the general-purpose listing tool that can be filtered by project, team, cycle, issue, etc., nor does it clarify when to use this over more specific document getters. The description is too minimal to be fully contextual for an agent to correctly choose this tool among the many document-related siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All ten parameters have descriptions in the schema (100% coverage), so the schema fully documents each parameter. The description adds no new parameter meaning; it doesn't clarify how filters interact or provide examples. Since the schema does the heavy lifting, the baseline of 3 applies. The description doesn't compensate for any gaps, but none exist at the field level.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get workspace documents from Linear' clearly identifies the action (get) and resource (documents), and the plural 'documents' implies a list operation, which distinguishes it from getDocumentById. However, it doesn't specify that this is a general listing tool with filters, and it's somewhat vague about the scope ('workspace documents' could be interpreted as all documents or a specific category). It's reasonably clear but not fully distinguishing among the many document-related siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like linear_getProjectDocuments, linear_getTeamDocuments, or linear_searchDocuments. It doesn't mention that this is the general-purpose document listing tool with optional filters, nor does it explain when to prefer specific getters. The schema shows filters like projectId, teamId, etc., but the description gives no advice on usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.